Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100307197> ?p ?o ?g. }
- W3100307197 abstract "Within psychology, neuroscience and artificial intelligence, there has been increasing interest in the proposal that the brain builds probabilistic models of sensory and linguistic input: that is, to infer a probabilistic model from a sample. The practical problems of such inference are substantial: the brain has limited data and restricted computational resources. But there is a more fundamental question: is the problem of inferring a probabilistic model from a sample possible even in principle? We explore this question and find some surprisingly positive and general results. First, for a broad class of probability distributions characterised by computability restrictions, we specify a learning algorithm that will almost surely identify a probability distribution in the limit given a finite i.i.d. sample of sufficient but unknown length. This is similarly shown to hold for sequences generated by a broad class of Markov chains, subject to computability assumptions. The technical tool is the strong law of large numbers. Second, for a large class of dependent sequences, we specify an algorithm which identifies in the limit a computable measure for which the sequence is typical, in the sense of Martin-Lof (there may be more than one such measure). The technical tool is the theory of Kolmogorov complexity. We analyse the associated predictions in both cases. We also briefly consider special cases, including language learning, and wider theoretical implications for psychology." @default.
- W3100307197 created "2020-11-23" @default.
- W3100307197 creator A5007418876 @default.
- W3100307197 creator A5029628745 @default.
- W3100307197 date "2017-08-04" @default.
- W3100307197 modified "2023-10-13" @default.
- W3100307197 title "Identification of Probabilities" @default.
- W3100307197 cites W1535030269 @default.
- W3100307197 cites W1547322272 @default.
- W3100307197 cites W1560408190 @default.
- W3100307197 cites W1567277581 @default.
- W3100307197 cites W1574036494 @default.
- W3100307197 cites W1597372857 @default.
- W3100307197 cites W1638203394 @default.
- W3100307197 cites W1967658564 @default.
- W3100307197 cites W1974881914 @default.
- W3100307197 cites W1980862600 @default.
- W3100307197 cites W1981403153 @default.
- W3100307197 cites W1981818098 @default.
- W3100307197 cites W1997396881 @default.
- W3100307197 cites W2013953457 @default.
- W3100307197 cites W2017357931 @default.
- W3100307197 cites W2042492924 @default.
- W3100307197 cites W2046809950 @default.
- W3100307197 cites W2054986668 @default.
- W3100307197 cites W2078828996 @default.
- W3100307197 cites W2079145130 @default.
- W3100307197 cites W2095734615 @default.
- W3100307197 cites W2098212071 @default.
- W3100307197 cites W2110485445 @default.
- W3100307197 cites W2110891220 @default.
- W3100307197 cites W2123713131 @default.
- W3100307197 cites W2126160338 @default.
- W3100307197 cites W2128211763 @default.
- W3100307197 cites W2132003317 @default.
- W3100307197 cites W2132960888 @default.
- W3100307197 cites W2135547275 @default.
- W3100307197 cites W2147336195 @default.
- W3100307197 cites W2148132004 @default.
- W3100307197 cites W2149365661 @default.
- W3100307197 cites W2153791616 @default.
- W3100307197 cites W2159080219 @default.
- W3100307197 cites W2292630385 @default.
- W3100307197 cites W2333790164 @default.
- W3100307197 cites W2504757423 @default.
- W3100307197 cites W2751862591 @default.
- W3100307197 cites W2953054747 @default.
- W3100307197 cites W2970241052 @default.
- W3100307197 cites W38903562 @default.
- W3100307197 cites W592574058 @default.
- W3100307197 cites W72959365 @default.
- W3100307197 hasPublicationYear "2017" @default.
- W3100307197 type Work @default.
- W3100307197 sameAs 3100307197 @default.
- W3100307197 citedByCount "1" @default.
- W3100307197 countsByYear W31003071972017 @default.
- W3100307197 crossrefType "journal-article" @default.
- W3100307197 hasAuthorship W3100307197A5007418876 @default.
- W3100307197 hasAuthorship W3100307197A5029628745 @default.
- W3100307197 hasBestOaLocation W31003071971 @default.
- W3100307197 hasConcept C105795698 @default.
- W3100307197 hasConcept C111142201 @default.
- W3100307197 hasConcept C11413529 @default.
- W3100307197 hasConcept C119857082 @default.
- W3100307197 hasConcept C124101348 @default.
- W3100307197 hasConcept C134306372 @default.
- W3100307197 hasConcept C144237770 @default.
- W3100307197 hasConcept C149441793 @default.
- W3100307197 hasConcept C151201525 @default.
- W3100307197 hasConcept C152062344 @default.
- W3100307197 hasConcept C154945302 @default.
- W3100307197 hasConcept C185592680 @default.
- W3100307197 hasConcept C198531522 @default.
- W3100307197 hasConcept C2776214188 @default.
- W3100307197 hasConcept C2777212361 @default.
- W3100307197 hasConcept C2778112365 @default.
- W3100307197 hasConcept C2779341405 @default.
- W3100307197 hasConcept C2780009758 @default.
- W3100307197 hasConcept C33923547 @default.
- W3100307197 hasConcept C41008148 @default.
- W3100307197 hasConcept C43617362 @default.
- W3100307197 hasConcept C49937458 @default.
- W3100307197 hasConcept C54355233 @default.
- W3100307197 hasConcept C86803240 @default.
- W3100307197 hasConcept C98763669 @default.
- W3100307197 hasConceptScore W3100307197C105795698 @default.
- W3100307197 hasConceptScore W3100307197C111142201 @default.
- W3100307197 hasConceptScore W3100307197C11413529 @default.
- W3100307197 hasConceptScore W3100307197C119857082 @default.
- W3100307197 hasConceptScore W3100307197C124101348 @default.
- W3100307197 hasConceptScore W3100307197C134306372 @default.
- W3100307197 hasConceptScore W3100307197C144237770 @default.
- W3100307197 hasConceptScore W3100307197C149441793 @default.
- W3100307197 hasConceptScore W3100307197C151201525 @default.
- W3100307197 hasConceptScore W3100307197C152062344 @default.
- W3100307197 hasConceptScore W3100307197C154945302 @default.
- W3100307197 hasConceptScore W3100307197C185592680 @default.
- W3100307197 hasConceptScore W3100307197C198531522 @default.
- W3100307197 hasConceptScore W3100307197C2776214188 @default.
- W3100307197 hasConceptScore W3100307197C2777212361 @default.